© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10391
    Prev
    Next
    INDEX
    Explanations

    administrative or directory services

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is almost exclusively activated by numeric tokens or number‐like strings (years, version numbers, digit sequences, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PCB
    0.70
     PCB
    0.67
    BTC
    0.62
     波
    0.60
     tmux
    0.60
    CLionProjects
    0.59
     गार्ड
    0.58
     CPU
    0.56
     Guarda
    0.56
    睡
    0.56
    POSITIVE LOGITS
    ldap
    1.08
     lacrosse
    0.91
     LDAP
    0.86
     ADMINISTRATIVE
    0.73
     Administrators
    0.73
     administrative
    0.71
     dn
    0.70
     Administrative
    0.68
    Administrative
    0.68
     Searches
    0.67
    Activations Density 0.201%

    No Known Activations